The online monitoring of battery energy storage systems (ESSs) is crucial to detecting sensor anomalies that could have detrimental impacts on the system’s safety, reliability, and availability. Model-based anomaly detection mechanisms could be integrated into battery management systems (BMSs) with modeling and estimation capabilities. However, previous model-based anomaly detection mechanisms have been tested only on small stacks of batteries or single cells.
On January 30, 2026, the article title “Scaling Up Online Model-Based Anomaly Detection Methods for Use in Large Battery Stacks” by Victoria A. O’Brien and Rodrigo D. Trevizan was published in the IEEE Industry Applications Magazine. The article follows O’Brien’s successful presentation of the paper “A Comparison of Online Model-Based Anomaly Detection Methods for a Lithium-Ion Battery Cell” at the 2024 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM). The article addresses a critical research gap by comparing four model-based anomaly detection methods for simulated stacks of 12 and 36 series-connected battery cells. The work evaluates the viability of four model-based anomaly detectors: the Chi-Squared test, Cumulative Sum algorithm (CUSUM), additive Chi-Squared test (ACST), and mean Shewhart control chart. The comparison focuses on false positive rates, detection accuracy, and computational burden. The CUSUM algorithm demonstrated superior performance, achieving a false positive rate of 0%, a detection accuracy of 99.6%, and maximum computational times of 0.0162 seconds and 0.0909 seconds per iteration for the 12-cell and 36-cell stacks, respectively. This study suggests that model-based anomaly detection algorithms can effectively scale for high-voltage battery management system applications, offering high accuracy, low false alarms, and manageable computational demands. The IEEE Industry Applications Magazine publishes articles that advance technological innovation and practical applications within industry. Research featured in the magazine reaches beyond the academic community to industry professionals.
Citation: V. A. O’Brien and R. D. Trevizan, “Scaling Up Online Model-Based Anomaly Detection Methods for Use in Large Battery Stacks: Addressing Challenges in Online Monitoring of Battery Systems,” in IEEE Industry Applications Magazine, doi: 10.1109/MIAS.2025.3648148. [Online] Available: https://ieeexplore.ieee.org/document/11366229
This material is based upon work supported by the U.S. Department of Energy, Office of Electricity (OE), Energy Storage Division.